Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1673 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0088. Min Act: -0.0003

Data Index: 651299 (C4 (Web Text))

Max Activating Token Index: 1007

Text #1

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0087. Min Act: -0.0003

Data Index: 1618890 (Python Code)

Max Activating Token Index: 267

Text #2

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0086. Min Act: -0.0003

Data Index: 1122264 (C4 (Web Text))

Max Activating Token Index: 516

Text #3

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0083. Min Act: -0.0003

Data Index: 1413914 (Python Code)

Max Activating Token Index: 254

Text #4

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0085. Min Act: -0.0003

Data Index: 986870 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0083. Min Act: -0.0003

Data Index: 631135 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0083. Min Act: -0.0003

Data Index: 734413 (C4 (Web Text))

Max Activating Token Index: 44

Text #7

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0083. Min Act: -0.0003

Data Index: 231063 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0082. Min Act: -0.0003

Data Index: 1641868 (Python Code)

Max Activating Token Index: 333

Text #9

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0084. Min Act: -0.0003

Data Index: 1398436 (Python Code)

Max Activating Token Index: 349

Text #10

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0082. Min Act: -0.0003

Data Index: 1613971 (Python Code)

Max Activating Token Index: 412

Text #11

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0082. Min Act: -0.0003

Data Index: 1551566 (Python Code)

Max Activating Token Index: 321

Text #12

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0082. Min Act: -0.0003

Data Index: 1565489 (Python Code)

Max Activating Token Index: 576

Text #13

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0081. Min Act: -0.0003

Data Index: 786607 (C4 (Web Text))

Max Activating Token Index: 103

Text #14

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0082. Min Act: -0.0003

Data Index: 410127 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0081. Min Act: -0.0003

Data Index: 1607931 (Python Code)

Max Activating Token Index: 273

Text #16

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0082. Min Act: -0.0003

Data Index: 732772 (C4 (Web Text))

Max Activating Token Index: 135

Text #17

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0082. Min Act: -0.0003

Data Index: 519396 (C4 (Web Text))

Max Activating Token Index: 150

Text #18

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0082. Min Act: -0.0003

Data Index: 1319031 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 0.0088. Min Range: -0.0088

Max Act: 0.0082. Min Act: -0.0004

Data Index: 1130425 (C4 (Web Text))

Max Activating Token Index: 977